|Publication number||US7885436 B2|
|Application number||US 11/825,412|
|Publication date||Feb 8, 2011|
|Priority date||Jul 13, 2006|
|Also published as||US20080013808, WO2008008292A2, WO2008008292A3|
|Publication number||11825412, 825412, US 7885436 B2, US 7885436B2, US-B2-7885436, US7885436 B2, US7885436B2|
|Inventors||Anthony P. Russo, Wayne Yang|
|Original Assignee||Authentec, Inc.|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (101), Non-Patent Citations (19), Referenced by (2), Classifications (11), Legal Events (5)|
|External Links: USPTO, USPTO Assignment, Espacenet|
This application claims priority under 35 U.S.C. §119(e) of the co-pending U.S. provisional patent application Ser. No. 60/830,768, filed Jul. 13, 2006, and titled “System for and Method for Assigning Confidence Values to Fingerprint Minutia Points,” which is hereby incorporated by reference.
This invention relates to biometric image processing. In particular, this invention relates to systems for and methods of assigning confidence values to identifying characteristics of a biometric object, such as fingerprints, using match results.
Automated fingerprint processing is a mature art whose application rapidly is becoming more widespread. Fingerprint minutiae matching algorithms methodically compare minutiae points to determine whether two fingerprint templates match each other. Typically, these matching algorithms rely upon an analysis of the confidence of each individual minutia to improve performance or to reduce the computational complexity of the matching process by pruning out low confidence minutiae.
Prior art systems assign these minutiae confidence values by analyzing local and global properties of the image from which they were detected and extracted. These image properties are not tightly linked to the actual matching process and therefore do not always produce a reliable confidence value that predicts how likely a minutia point is to be matched in future verification attempts. It is the estimate of this likelihood that is most important when pruning or truncating the number of minutiae in a template.
Nothing in the prior art teaches assigning confidence values or pruning of individual templates.
The present invention assigns confidence values to individual minutiae in a fingerprint template by using the results of matching multiple templates to each other, where each template is created by scanning a different image of the same finger. Because the present invention relies on matching to estimate the probability of future matches, the results are very reliable and are an excellent predictor of the likelihood of a minutia point to be accurately matched in future verification or identification attempts. Another advantage of this method is that the confidence values can be re-evaluated, and made more reliable, with additional minutia template data and without having access to the original fingerprint image. This is not possible using prior art systems.
In a first aspect of the present invention, a method is used to organize identifying characteristics of a patterned object used to verify the patterned object. The method includes matching identifying characteristics of the patterned object in one or more sets with identifying characteristics of the patterned object in a candidate set. The method also includes adjusting a confidence value of each identifying characteristic in the one or more sets based on results of the matching, and organizing the one or more sets based on the confidence values.
The one or more sets are organized by ordering the identifying characteristics in the one or more sets based on the confidence values, by deleting from the one or more sets any identifying characteristics with a confidence value below a threshold, or both. In one embodiment, the threshold is predetermined. Alternatively, the threshold is dynamic.
In one embodiment, the identifying characteristics are fingerprint minutiae and the candidate set and the one or more sets each forms a template of fingerprint minutiae. In another embodiment, the identifying characteristics correspond to retinal minutiae and the candidate set and the one or more sets each forms a template corresponding to retinal minutiae. As used herein, “retinal minutiae” refer to blood vessel bifurcations, endings, and the like. In one embodiment, the method also includes adding the candidate set to the one or more sets.
In a second aspect of the present invention, a method of verifying a patterned object includes generating a template of candidate identifying characteristics from an image of the patterned object; matching the candidate identifying characteristics to stored identifying characteristics of the patterned object in one or more other templates, wherein the matches are performed based on confidence values associated with each of the stored identifying characteristics; and verifying the patterned object based on a result of the matches. As used herein, a “match” is an attempt to match characteristics, and results in either a “successful” or an “unsuccessful” match.
In one embodiment, the identifying characteristics are finger minutiae. In this embodiment, the method also includes reading the image of the patterned object using a finger sensor. In another embodiment, the identifying characteristics include retinal minutiae. In this other embodiment, the method also includes reading the image of the patterned object using a retinal scanner. The one or more other templates are generated from one or more images of the patterned object.
The candidate identifying characteristics are matched to the stored identifying characteristics in a manner based on the confidence values. Preferably, the manner is in an order from highest to lowest confidence values. The method also includes aligning a template of the candidate identifying characteristics with the one or more other templates, to thereby perform a more accurate match.
In a third aspect of the present invention, a method of generating templates corresponding to image data includes performing one or more pairwise matches of two or more templates each containing data corresponding to identifying characteristics, and assigning confidence values to each identifying characteristic in each of the two or more templates based on matches between the identifying characteristics.
In one embodiment, confidence values are assigned to an identifying characteristic by updating confidence values associated with the identifying characteristic by an incremental value. The incremental value depends on a type of match between identifying characteristics matched during the pairwise matches. The match is “unsuccessful match”, “successful loose” match, “successful strict” match, a successful match within a bounding box, or a combination of these.
Preferably, each pairwise match includes a first stage that includes a loose or low-tolerance match, and a second stage that includes a strict or high-tolerance match.
In a fourth aspect of the present invention, an apparatus for assigning confidence values to identifying characteristics of a patterned object includes a template builder and an assignor. The template builder is configured to build templates of identifying characteristics. Each template contains a record mapping a confidence value to an associated identifying characteristic. The assignor is configured to assign confidence values to each of the identifying characteristics generated from a match of each of the identifying characteristics in a first template to identifying characteristics of the patterned object in one or more other templates. The assignor is also configured to organize each of the records according to the confidence values. In one embodiment the template builder discards all identifying characteristics below a threshold. As used herein, configured means configured using software, hardware, firmware, any other means of configuring an element, and any combination of these.
The apparatus also includes a biometric sensor coupled to the template builder. The biometric sensor is configured to read a patterned object and extract data corresponding to identifying characteristics. In one embodiment, the biometric sensor is a finger image sensor. In another embodiment, the biometric sensor is a retinal scanner.
Preferably, the apparatus also includes a template library configured to store one or more templates containing records mapping confidence values to identifying characteristics. The apparatus also includes a matcher for matching, in a predetermined manner, identifying characteristics of the patterned object read by the biometric sensor with identifying characteristics in the template library, thereby verifying the patterned object. The predetermined manner includes comparing the identifying characteristics in an order determined by the confidence values.
Preferably, the matcher includes a loose matcher in a first stage and a strict matcher in a second stage. The matcher is configured to increment a confidence value by a first value if the first stage determines a successful match and by a second value, larger than the first value, if the second stage determines a successful match.
The apparatus also includes a host device configured to perform a function based on a successful match between a candidate template and a template within the template library. The host device is a cellular phone, a personal computer, a digital camera, a digital audio player, a digital audio/video player, or a health/monitor device.
In a fifth aspect of the present invention, an apparatus for matching minutiae of a patterned object includes a finger sensor for reading an image of the patterned object; a template builder configured to build templates of minutiae from the image; a storage containing a library of one or more other templates, wherein each of the one or more templates maps confidence values to minutiae from one image of the patterned object, and further wherein the minutiae in the one or more templates have an organization based on the confidence values; and a matcher configured to match any pair of templates based on the organization to thereby verify the patterned object. The apparatus also includes an assignor configured to assign confidence values to minutiae in the one or more templates based on a result of the matches and to organize templates based on the confidence values.
In a sixth aspect of the present invention, a computer-readable medium stores a data structure that includes a plurality of records. Each record includes a first field containing data representing a minutia point and a second field containing data representing a confidence value for the minutia point.
The present invention is used to validate a patterned object, such as a finger, by matching the identifying characteristics of the patterned object with stored identifying characteristics of the patterned object. Matches are performed based on confidence values associated with the identifying characteristics. For example, those identifying characteristics with the highest confidence values are first matched to identifying characteristics of the read patterned image. In other embodiments, data corresponding to identifying characteristics with low confidence values are deleted, thereby saving memory, always a consideration on portable devices such as cellular telephones, digital cameras, and digital audio players.
It will be appreciated that patterned images other than fingers and eyes are able to be verified, and identifying characteristics other than retinal minutiae can also be used in accordance with the present invention.
As one example, an identifying characteristic has a high degree of confidence (a high confidence value) because it is found in more of the patterned images than an identifying characteristic with a smaller confidence value. An identifying characteristic can have a low confidence value because it is associated with a temporary scar that is found in few of the scanned images or was produced by dirt on a sensor from which the patterned image was obtained. In accordance with the present invention, when verifying a scanned image, scanned identifying characteristics are first matched to corresponding identifying characteristics that have high confidence values. In some embodiments, identifying characteristics with low confidence values are not even stored, let alone matched, thereby saving memory and processor time needed to perform matches.
When a number of identifying characteristics above a threshold are successfully matched with stored identifying characteristics, the patterned object, and thus the owner of the patterned object, is verified. This threshold can be set and adjusted using different criteria. As one example, when a user must be verified to perform some low-level task on a computer system, few identifying characteristics must be successfully matched. When a user must be verified to perform a high-level task, more identifying characteristics must successfully match.
In one embodiment, a minutiae-based matcher is used to compare two or more templates extracted from two or more different scans of the same fingerprint to assign confidence values to each individual minutia point in each template. Minutiae matchers are described in Davide Maltoni, Dario Maio, Anil K. Jain, and Salil Prabhakar, Handbook of Fingerprint Recognition (1st ed., Springer 2005), which is hereby incorporated by reference. These minutiae matchers are able to determine whether a minutia point M in template T_view1 is the same physical point as minutia point M′ in template T_view2. In fact, the matcher is able to map a subset of minutia points in T_view1 to a subset of the minutia points in T_view2, so that for any given minutia point M in template T_view1, it is known whether a) that point has a corresponding point M′ in template T_view2 or b) that point has no known corresponding point. Furthermore, it can be determined whether a point M that does not have a corresponding point M′, lies within the bounding box of matched minutiae points in T_view1 or is external to it. A similar analysis is performed for all minutiae points in T_view2. Fingerprint matchers are discussed in more detail in U.S. Pat. No. 6,546,122, titled “Method for Combining Fingerprint Templates Representing Various Sensed Areas,” to Russo, and U.S. Pat. No. 6,681,034, titled “Method and System for Fingerprint Template Matching,” to Russo, both of which are hereby incorporated by reference.
As described in more detail below, confidence values are also adjusted depending on the location of minutiae: those within a bounding box are adjusted by a larger increment than those outside the bounding box. A bounding box is used for many reasons, such as tailoring processing and simplifying the matching algorithm, thus decreasing the amount of processing that must be performed during a match.
For all minutiae contained in T_view1 and T_view2, confidence values are assigned and updated as follows:
The bounding box in the preferred embodiment is defined as the rectangle that minimally encloses all the matched minutia points. Those skilled in the art will appreciate that other definitions are possible, including ones where the rectangle is rotated, translated, or otherwise oriented to match the angle of rotation between the two fingerprints and another in which a trapezoid or other polygonal shape is used to enclose the matched points.
If a minutia point is not successfully matched but lies outside the bounding box, it likely had no chance to successfully match because it came from a part of the finger that did not overlap with the image it was being matched to. Therefore it is not penalized.
In a preferred embodiment, a matcher has two stages. The first stage uses looser tolerances to match the minutiae points, followed by a second final stage that uses more stringent (e.g., stricter or tighter) tolerances. The first stage is less likely to omit a minutia point that should have successfully matched, so therefore it adds some information to the confidence. It is also possible to run a single-stage matcher twice with different parameter settings—one loose and one tighter—to get similar results. It will be appreciated by those skilled in the art that any number of stages and parameter settings, alone or combined, can be used to generate finer granularity in the confidence values, as could numerous matching metrics such as match error that can be calculated on a per-minutia basis. In the latter case, the confidence increments C_external, C_matchFinal, and C_noMatch are not fixed constants.
In all of these cases the bounding box is still defined as a rectangle that minimally encloses the final matched minutia points. However, in alternative embodiments the bounding box is defined by those minutiae points that passed the first stage instead of the final one. Or, different bounding boxes are used based on the results of executing each stage and/or parameter setting.
In a preferred embodiment, for all minutiae contained in T_view1 and T_view2, confidence values are assigned as follows:
In one embodiment C_noMatch=0, C_external=2, C_matchStagel=8 and C_matchFinal=32. These incremental values represent the relative importance of each stage and property. However, other values and weightings are possible, including values less than zero.
The process is able to be repeated for multiple templates simply by matching more templates to each other and assigning the confidence values as shown above. For instance, if a pool of three templates T_view1, T_view2 and T_view3 instead of just two are available, all confidence values are set to zero and then all possible pairs of templates are run through the confidence assignment as follows, in any order:
More generally, all pairwise combinations are performed for all N templates. Given a large enough pool it could be advantageous to skip some pairs to save computer resources. It is possible to assign confidence values at a given time—most likely during the enrollment process—and then modify (adjust) them using additional template data captured at a later date—most likely during subsequent verification attempts.
In an alternative embodiment, the minutia confidence adjustment technique described above is used in conjunction with prior art minutia confidence methods to form a hybrid method that could be more accurate than either technique alone. In yet another alternative embodiment, the minutia confidence adjustment technique is applied to only enrollment templates and prior art techniques are used on templates acquired during verification, where only a single template might be available.
In operation, when a fingerprint image is to be verified, the records in the “candidate” template generated when the finger is scanned are matched to the records in the template 500. The scanned (candidate) minutiae points are matched to the minutiae points in the template 500 to determine whether sufficient minutiae points between the two successfully match. The template 500′ is considered to reflect minutiae of an authentic finger image. The candidate minutiae are first matched to the minutiae in the template 500′, and if a number of minutiae points above a threshold successfully match, the scanned finger is verified. Generally, the records are compared sequentially, which means that some minutiae with low confidence values are matched before minutiae with higher confidence values are matched. This is inefficient since the verification process can be performed more quickly by matching minutiae that are more likely in both templates. Moreover, the entire template 500′ is stored in memory. And because a system can store many templates, each containing many minutiae points, memory is wasted.
In accordance with the present invention, the template 500′ is reorganized to produce the template 500″ in
Preferably, the template 500″ is also pruned so that minutiae points with a confidence value below a threshold are deleted from the template 500″, thereby saving memory. For example, if a pruning threshold is 10 and the minutiae points C, D, and F all have confidence values less than 10, then records for all of these minutiae points are deleted from the table 500″.
In the preferred embodiment, pruning is done by ordering the minutiae by confidence and truncating the lowest confidence points or just enough so as not to exceed the system's maximum minutiae requirement, if there is one. Each template is pruned separately. In alternative embodiments, pruning is performed based on additional factors as well as confidence value, including ways that maximize coverage of the physical surface area of the fingerprint represented by the templates (e.g., T_view1, T_view2, etc, described in relation in
The pruning threshold can be static, such as determined during an initialization step, or it can be dynamic, such as based on the available memory in the system. When the available memory is limited, the threshold can be increased so that smaller templates are stored in memory. The threshold can also be set based on a security level of a system. For lower security levels, the threshold is higher, so that fewer minutiae points need to be matched. Templates are correspondingly smaller.
In another embodiment, a threshold can also be determined by a sum of confidence values. In this embodiment, confidence values are added, so that the sum of the confidence values in the stored templates is at or near a predetermined threshold. Thus, if the threshold is 80, minutiae points whose confidence values sum to 80 are stored. All other minutiae points are deleted. This threshold can be increased when more scans are performed. In this way, minutiae points are stored based on the relative values of the confidence values, not just the overall sum.
In other words, no matter how many scans are performed, if the relative confidence values remain unchanged, the size of the template also remains unchanged. In this embodiment, again, the threshold is dynamic. It will be appreciated that other pruning algorithms are possible in accordance with the present invention.
If, in the step 605, a threshold number of minutiae do not successfully match, the process continues to step 609, in which it is determined whether there are more templates in the template library to check. If there are no more templates in the template library, the process proceeds to the step 613, in which the process generates an “Unsuccessful Template Match” (“Verification failed”) result, and then on to step 615. If, in the step 609, it is determined that there are more templates in the template library to check, the process proceeds to the step 611, in which the next template is retrieved, and the process then loops back to the step 603.
It will be appreciated that while the discussion above describes a template corresponding to an image of a single patterned object, templates of multiple patterned objects can also be used in accordance with the present invention. For example, the present invention can be used to verify different fingers of a single user or fingers of different users.
Preferably, the confidence adjustor 260 is the same component as a confidence assignor, discussed elsewhere. The single element assigns values during system initialization and adjusts those values later, whenever additional images of a biometric object are scanned. In some embodiments, the single element is referred to as either a confidence adjustor or a confidence assignor, depending on which step of the process (initialization or updating) is being performed. In other embodiments, the confidence adjustor and the confidence assignor are different elements.
In operation of one embodiment of the present invention, multiple scans of finger images are taken. Corresponding templates from each scan are generated and stored in a template library. Preferably, the multiple scans are taken of the finger at different orientations-rotated along different axis, rolled, etc.—so that when the finger is later scanned for verification, regardless of its orientation, a corresponding template exists. The templates are matched to one another, using pairwise matches, and confidence values are determined for each minutiae in each template. The templates are organized so that they take up less memory and so that they can be later matched to other templates more quickly. Preferably, the multiple scans are performed during an orientation or initialization step.
The templates are later used to verify a user's identity. The user places her finger on or swipes her finger across a finger sensor. A candidate template is generated from this scan and matched to the templates in the template library. The matches are performed based on the organization of the templates in the template library. A user is verified only if a successful match is made between the candidate template and a template in the template library. In some embodiments, the candidate template is added to the template library. Once verified, the user can access a system or perform a specific function on the system, such as access a protected file or launch a specific program.
While the discussions above have focused on fingerprint sensors, it will be appreciated that the invention can be used to verify other biometric objects such as retinas, using identifying characteristics such as retinal minutiae, and palmprints. Those skilled in the art will recognize that the invention can be modified in many ways. For example, a template in accordance with the present invention can point to a different data structure in which identifying characteristics are actually stored. In this way, the template will contain elements that correspond to the identifying characteristics. It is these elements that can be ranked, ordered, or deleted in accordance with the present invention.
It will also be appreciated that the steps shown above to illustrate embodiments of the invention can be modified in many ways in accordance with the invention. For example, some steps can be added, some steps can be deleted, and the steps can be performed in orders different from those shown.
It will be readily apparent to one skilled in the art that other modifications may be made to the embodiments without departing from the spirit and scope of the invention as defined by the appended claims.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US5283735||Dec 4, 1992||Feb 1, 1994||Biomechanics Corporation Of America||Feedback system for load bearing surface|
|US5327161||Oct 21, 1991||Jul 5, 1994||Microtouch Systems, Inc.||System and method for emulating a mouse input device with a touchpad input device|
|US5610993 *||Dec 10, 1992||Mar 11, 1997||Yozan Inc.||Method of co-centering two images using histograms of density change|
|US5612719||Apr 15, 1994||Mar 18, 1997||Apple Computer, Inc.||Gesture sensitive buttons for graphical user interfaces|
|US5666113||Sep 5, 1995||Sep 9, 1997||Microtouch Systems, Inc.||System for using a touchpad input device for cursor control and keyboard emulation|
|US5689285||May 2, 1995||Nov 18, 1997||Asher; David J.||Joystick with membrane sensor|
|US5740276||Jul 27, 1995||Apr 14, 1998||Mytec Technologies Inc.||Holographic method for encrypting and decrypting information using a fingerprint|
|US5825352||Feb 28, 1996||Oct 20, 1998||Logitech, Inc.||Multiple fingers contact sensing method for emulating mouse buttons and mouse operations on a touch sensor pad|
|US5825907||Jul 11, 1997||Oct 20, 1998||Lucent Technologies Inc.||Neural network system for classifying fingerprints|
|US5862248||Jun 27, 1996||Jan 19, 1999||Harris Corporation||Integrated circuit device having an opening exposing the integrated circuit die and related methods|
|US5909211||Mar 25, 1997||Jun 1, 1999||International Business Machines Corporation||Touch pad overlay driven computer system|
|US5940526||May 16, 1997||Aug 17, 1999||Harris Corporation||Electric field fingerprint sensor having enhanced features and related methods|
|US5963679||Jan 26, 1996||Oct 5, 1999||Harris Corporation||Electric field fingerprint sensor apparatus and related methods|
|US5995084||Jan 17, 1997||Nov 30, 1999||Tritech Microelectronics, Ltd.||Touchpad pen-input and mouse controller|
|US5995623||Jan 27, 1997||Nov 30, 1999||Fuji Xerox Co., Ltd.||Information processing apparatus with a software protecting function|
|US5995630||Feb 28, 1997||Nov 30, 1999||Dew Engineering And Development Limited||Biometric input with encryption|
|US6011849||Aug 28, 1997||Jan 4, 2000||Syndata Technologies, Inc.||Encryption-based selection system for steganography|
|US6035398||Nov 14, 1997||Mar 7, 2000||Digitalpersona, Inc.||Cryptographic key generation using biometric data|
|US6057830||Jan 17, 1997||May 2, 2000||Tritech Microelectronics International Ltd.||Touchpad mouse controller|
|US6061051||Jan 17, 1997||May 9, 2000||Tritech Microelectronics||Command set for touchpad pen-input mouse|
|US6135958||Aug 6, 1998||Oct 24, 2000||Acuson Corporation||Ultrasound imaging system with touch-pad pointing device|
|US6141753||Feb 10, 1998||Oct 31, 2000||Fraunhofer Gesellschaft||Secure distribution of digital representations|
|US6208329||Aug 13, 1996||Mar 27, 2001||Lsi Logic Corporation||Supplemental mouse button emulation system, method and apparatus for a coordinate based data input device|
|US6219793||Sep 8, 1997||Apr 17, 2001||Hush, Inc.||Method of using fingerprints to authenticate wireless communications|
|US6219794||Oct 8, 1997||Apr 17, 2001||Mytec Technologies, Inc.||Method for secure key management using a biometric|
|US6248655||Feb 29, 2000||Jun 19, 2001||Nippon Telegraph And Telephone Corporation||Method of fabricating a surface shape recognition sensor|
|US6259804||May 16, 1997||Jul 10, 2001||Authentic, Inc.||Fingerprint sensor with gain control features and associated methods|
|US6317508||Jan 13, 1998||Nov 13, 2001||Stmicroelectronics, Inc.||Scanning capacitive semiconductor fingerprint detector|
|US6330345||Nov 17, 1997||Dec 11, 2001||Veridicom, Inc.||Automatic adjustment processing for sensor devices|
|US6408087||Jan 13, 1998||Jun 18, 2002||Stmicroelectronics, Inc.||Capacitive semiconductor user input device|
|US6518560||Apr 27, 2000||Feb 11, 2003||Veridicom, Inc.||Automatic gain amplifier for biometric sensor device|
|US6535622 *||Apr 26, 1999||Mar 18, 2003||Veridicom, Inc.||Method for imaging fingerprints and concealing latent fingerprints|
|US6546122 *||Jul 29, 1999||Apr 8, 2003||Veridicom, Inc.||Method for combining fingerprint templates representing various sensed areas of a fingerprint to derive one fingerprint template representing the fingerprint|
|US6601169||Oct 31, 2001||Jul 29, 2003||Clyde Riley Wallace, Jr.||Key-based secure network user states|
|US6661631||Sep 9, 2000||Dec 9, 2003||Stmicroelectronics, Inc.||Automatic latchup recovery circuit for fingerprint sensor|
|US6667439||Aug 16, 2001||Dec 23, 2003||Authentec, Inc.||Integrated circuit package including opening exposing portion of an IC|
|US6668072 *||Nov 8, 2000||Dec 23, 2003||Siemens Aktiengesellschaft||Method for producing a reference image for pattern recognition tasks|
|US6681034 *||Jul 15, 1999||Jan 20, 2004||Precise Biometrics||Method and system for fingerprint template matching|
|US6744910||Oct 29, 1999||Jun 1, 2004||Cross Match Technologies, Inc.||Hand-held fingerprint scanner with on-board image normalization data storage|
|US6754365||Feb 16, 2000||Jun 22, 2004||Eastman Kodak Company||Detecting embedded information in images|
|US6804378||Feb 12, 2003||Oct 12, 2004||Digimarc Corporation||Methods and products employing biometrics and steganography|
|US6876756||Nov 18, 2001||Apr 5, 2005||Thomas Vieweg||Container security system|
|US6961452 *||Mar 12, 2001||Nov 1, 2005||Fujitsu Limited||Fingerprint data synthesis method, fingerprint data synthesis apparatus and computer-readable recording medium on which fingerprint data synthesis program is recorded as well as biometric information synthesis method|
|US7002553||Jul 22, 2004||Feb 21, 2006||Mark Shkolnikov||Active keyboard system for handheld electronic devices|
|US7003670||Jun 8, 2001||Feb 21, 2006||Musicrypt, Inc.||Biometric rights management system|
|US7020270||Oct 27, 2000||Mar 28, 2006||Firooz Ghassabian||Integrated keypad system|
|US7054470||Sep 3, 2003||May 30, 2006||International Business Machines Corporation||System and method for distortion characterization in fingerprint and palm-print image sequences and using this distortion as a behavioral biometrics|
|US7113179||Jun 23, 2004||Sep 26, 2006||Interlink Electronics, Inc.||Force sensing resistor with calibration element and method of manufacturing same|
|US7136514||Feb 25, 2003||Nov 14, 2006||Wong Jacob Y||Method for authenticating an individual by use of fingerprint data|
|US7197168 *||Jul 12, 2002||Mar 27, 2007||Atrua Technologies, Inc.||Method and system for biometric image assembly from multiple partial biometric frame scans|
|US7263212 *||Sep 8, 2003||Aug 28, 2007||Nec Corporation||Generation of reconstructed image data based on moved distance and tilt of slice data|
|US7280679||Apr 7, 2005||Oct 9, 2007||Atrua Technologies, Inc.||System for and method of determining pressure on a finger sensor|
|US7299360||Dec 16, 2003||Nov 20, 2007||Precise Biometrics||Method and system for fingerprint template matching|
|US7339572||Feb 26, 2007||Mar 4, 2008||Immersion Corporation||Haptic devices using electroactive polymers|
|US7369688 *||May 9, 2001||May 6, 2008||Nanyang Technological Univeristy||Method and device for computer-based processing a template minutia set of a fingerprint and a computer readable storage medium|
|US7474772||Jun 21, 2004||Jan 6, 2009||Atrua Technologies, Inc.||System and method for a miniature user input device|
|US20010017934||Dec 15, 2000||Aug 30, 2001||Nokia Mobile Phones Lt'd.||Sensing data input|
|US20020130673||Dec 6, 2001||Sep 19, 2002||Sri International||Electroactive polymer sensors|
|US20020186203||Feb 28, 2002||Dec 12, 2002||Yu-Fu Huang||Wireless remote control device for notebook computers|
|US20020188854||Jun 8, 2001||Dec 12, 2002||John Heaven||Biometric rights management system|
|US20030002718||May 28, 2002||Jan 2, 2003||Laurence Hamid||Method and system for extracting an area of interest from within a swipe image of a biological surface|
|US20030021495||Mar 13, 2002||Jan 30, 2003||Ericson Cheng||Fingerprint biometric capture device and method with integrated on-chip data buffering|
|US20030028811||Jul 9, 2001||Feb 6, 2003||Walker John David||Method, apparatus and system for authenticating fingerprints, and communicating and processing commands and information based on the fingerprint authentication|
|US20030044051||Aug 22, 2002||Mar 6, 2003||Nec Corporation||Fingerprint image input device and living body identification method using fingerprint image|
|US20030115490||Jul 12, 2002||Jun 19, 2003||Russo Anthony P.||Secure network and networked devices using biometrics|
|US20030123714||Nov 4, 2002||Jul 3, 2003||O'gorman Lawrence||Method and system for capturing fingerprints from multiple swipe images|
|US20030126448||Jul 12, 2002||Jul 3, 2003||Russo Anthony P.||Method and system for biometric image assembly from multiple partial biometric frame scans|
|US20030135764||Jan 14, 2002||Jul 17, 2003||Kun-Shan Lu||Authentication system and apparatus having fingerprint verification capabilities thereof|
|US20030214481||May 14, 2002||Nov 20, 2003||Yongming Xiong||Finger worn and operated input device and method of use|
|US20040014457||Dec 19, 2002||Jan 22, 2004||Stevens Lawrence A.||Systems and methods for storage of user information and for verifying user identity|
|US20040128521||Dec 16, 2003||Jul 1, 2004||Precise Biometrics||Method and system for fingerprint template matching|
|US20040148526||Jan 24, 2003||Jul 29, 2004||Sands Justin M||Method and apparatus for biometric authentication|
|US20040156538||Sep 8, 2003||Aug 12, 2004||Manfred Greschitz||Fingerprint sensor with potential modulation of the ESD protective grating|
|US20040186882||Mar 21, 2003||Sep 23, 2004||Ting David M.T.||System and method for audit tracking|
|US20040208348||Apr 18, 2003||Oct 21, 2004||Izhak Baharav||Imaging system and apparatus for combining finger recognition and finger navigation|
|US20040252867||Feb 19, 2002||Dec 16, 2004||Je-Hsiung Lan||Biometric sensor|
|US20040258282||Apr 12, 2004||Dec 23, 2004||Bjorn Vance C.||Fingerprint recognition system|
|US20040263479||Jul 22, 2004||Dec 30, 2004||Mark Shkolnikov||Active keyboard system for handheld electronic devices|
|US20050012714||Jun 21, 2004||Jan 20, 2005||Russo Anthony P.||System and method for a miniature user input device|
|US20050041885||Aug 4, 2004||Feb 24, 2005||Russo Anthony P.||System for and method of generating rotational inputs|
|US20050144329||Aug 17, 2004||Jun 30, 2005||Chih-Ming Tsai||Switch control system and method for a plurality of input devices|
|US20050169503||Jun 30, 2004||Aug 4, 2005||Howell Mark J.||System for and method of finger initiated actions|
|US20050179657||Feb 10, 2005||Aug 18, 2005||Atrua Technologies, Inc.||System and method of emulating mouse operations using finger image sensors|
|US20050259851||May 21, 2004||Nov 24, 2005||Fyke Steven H||Apparatus and method of input and finger print recognition on a handheld electronic device|
|US20050259852||Sep 21, 2004||Nov 24, 2005||Anthony Russo||Secure system and method of creating and processing partial finger images|
|US20060002597||Jul 8, 2005||Jan 5, 2006||Lumidigm, Inc.||Liveness sensor|
|US20060034043||Aug 8, 2005||Feb 16, 2006||Katsumi Hisano||Electronic device, control method, and control program|
|US20060078174||Apr 7, 2005||Apr 13, 2006||Atrua Technologies, Inc.||System for and method of determining pressure on a finger sensor|
|US20060103633||Feb 14, 2005||May 18, 2006||Atrua Technologies, Inc.||Customizable touch input module for an electronic device|
|US20060242268||Jul 1, 2005||Oct 26, 2006||General Electric Company||Mobile radiology system with automated DICOM image transfer and PPS queue management|
|US20060280346||Aug 18, 2006||Dec 14, 2006||Akihiro Machida||Fingerprint verification device|
|US20070014443||Jul 10, 2006||Jan 18, 2007||Anthony Russo||System for and method of securing fingerprint biometric systems against fake-finger spoofing|
|US20070016779||Aug 4, 2006||Jan 18, 2007||Lyle James D||Method and apparatus for encrypting data transmitted over a serial link|
|US20070034783||Mar 12, 2004||Feb 15, 2007||Eliasson Jonas O P||Multitasking radiation sensor|
|US20070038867||Jun 2, 2004||Feb 15, 2007||Verbauwhede Ingrid M||System for biometric signal processing with hardware and software acceleration|
|US20070061126||Sep 1, 2005||Mar 15, 2007||Anthony Russo||System for and method of emulating electronic input devices|
|US20070067642||Sep 13, 2006||Mar 22, 2007||Singhal Tara C||Systems and methods for multi-factor remote user authentication|
|US20070125937||Sep 9, 2004||Jun 7, 2007||Eliasson Jonas O P||System and method of determining a position of a radiation scattering/reflecting element|
|US20070146349||Dec 27, 2005||Jun 28, 2007||Interlink Electronics, Inc.||Touch input device having interleaved scroll sensors|
|US20070274575||Feb 16, 2007||Nov 29, 2007||Russo Anthony P||Method and system for biometric image assembly from multiple partial biometric frame scans|
|JP2000056877A||Title not available|
|1||"A Minutia-Based Partial Fingerprint Recognition System", Tsai-Yang Jea and Venu Govindaraju, Center for Unified Biometrics and Sensors, University at Buffalo, State of University of New York, Amherst, NY USA 14228, 22 pages.|
|2||"A Minutia-Based Partial Fingerprint Recognition System", Tsai—Yang Jea and Venu Govindaraju, Center for Unified Biometrics and Sensors, University at Buffalo, State of University of New York, Amherst, NY USA 14228, 22 pages.|
|3||"Handbook of Fingerprinting Recognition", Davide Maltoni et al., 2003 Springer Science Business Media, Inc., 8 pages.|
|4||"Learning Fingerprint Minutiae Location and Type", Salil Prabhakar et al., Sep. 3, 2000, 22 pages.|
|5||"NIST Fingerprint Image Quality", Eham Tabassi, Biometirc Consortium Conference, Sep. 20, 2005, 13 pages.|
|6||*||C. Ryu, Y. Han and H. Kim, "Super-template Generation Using Successive Bayesian Estimation for Fingerprint Enrollment," Proc. AVBPA 2005, pp. 710-719, 2005.|
|7||*||C. Ryu, Y. Han and H. Kim, "Super-template Generation Using Successive Bayesian Estimation for Fingerprint Enrollment," Proc. AVBPA 2005, pp. 710-719, 2005.|
|8||Criminal Justice Information Services (CJIS), "Electronic Fingerprint Transmission Specification", May 2, 2005, Prepared by Federal Bureau of Investigation, Criminal Justice Information Services Division, 1000 Custer Hollow Road, Clarksburg, WV 26306, 20 pages.|
|9||International Standard, ISO/IEC 19794-2, First Edition, Sep. 15, 2005, "Information Technology, Biometric Data Interchange Formats", Part 2: "Finer Minutiae Data", 40 pages.|
|10||*||Kyung Deok Yu, Sangsin Na, Tae Young Choi: A Fingerprint Matching Algorithm Based on Radial Structure and a Structure-Rewarding Scoring Strategy. AVBPA 2005: 656-664.|
|11||*||Lee, K. Choi, S. Lee and J. Kim, "Fingerprint Fusion Based on Minutiae and Ridge for Enrollment," Proc. AVBPA 2003, LNCS 2688, pp. 478-485, 2003.|
|12||*||M. Irani and S. Peleg, "Improving Resolution by Image Registration", published in the journal CVGIP: Graphical Models and Image Processing, vol. 53, pp. 231-239, May 1991.|
|13||NIST Biometric Data Specification for Personal Identity Verification, Charles Wilson et al., Jan. 2007, 27 pages.|
|14||*||Sasakawa et al., "Personal Verification System With High Tolerance of Poor Quality Fingerprints", The Transactions of the Institute of Electronics, Information and Communication Engineers, D-II, vol. J72-D-II, No. 5, pp. 707-714, May 1989.|
|15||*||W. Yau, K. Toh and T. Chen, "Fingerprint Templates Combination," Proc. 5th Chinese Conference on Biometric Recognition, LNCS 3338, pp. 449-460, 2004.|
|16||*||X. Jiang and W. Yau, "Fingerprint minutiae matching based on the local and global structures," in: Proceedings of ICPR, Barcelona, 2000, pp. 1038-1041.|
|17||*||X.D. Jiang and W.Y. Yau "Fingerprint Minutiae Matching Based on the Local and Global Structures," Proc. 15.sup.th International Conference on Pattern Recognition, ICPR, Barcelona, Spain, vol. 2, pp. 1042-1045, Sep. 2000.|
|18||*||X.D. Jiang, W.Y. Yau and W. Ser, "Detecting the Fingerprint Minutiae by Adaptive Tracing the Gray Level Ridge," Pattern Recognition, vol. 34, pp. 999-1013, May 2001.|
|19||*||Zheng et al, "A computational vision approach to image registration", Image Processing, IEEE Transactions on Volume 2, Issue 3, Jul. 1993 pp. 311-326.|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US9282284 *||May 20, 2013||Mar 8, 2016||Cisco Technology, Inc.||Method and system for facial recognition for a videoconference|
|US20140340467 *||May 20, 2013||Nov 20, 2014||Cisco Technology, Inc.||Method and System for Facial Recognition for a Videoconference|
|U.S. Classification||382/124, 340/5.83, 340/5.53, 382/115|
|International Classification||G06T7/00, G06K9/00, G06T1/00|
|Cooperative Classification||G06K9/00026, G06K9/00067|
|European Classification||G06K9/00A1C, G06K9/00A2|
|Aug 30, 2007||AS||Assignment|
Owner name: ATRUA TECHNOLOGIES, INC., CALIFORNIA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:RUSSO, ANTHONY P.;YANG, WAYNE;REEL/FRAME:019785/0769
Effective date: 20070719
|Jul 22, 2009||AS||Assignment|
Owner name: AUTHENTEC, INC., FLORIDA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:ATRUA, LLC;REEL/FRAME:022980/0901
Effective date: 20090708
Owner name: AUTHENTEC, INC.,FLORIDA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:ATRUA, LLC;REEL/FRAME:022980/0901
Effective date: 20090708
|Jul 19, 2012||AS||Assignment|
Owner name: ATRUA, LLC, CALIFORNIA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:ATRUA TECHNOLOGIES, INC.;REEL/FRAME:028591/0058
Effective date: 20090531
|Jul 9, 2014||FPAY||Fee payment|
Year of fee payment: 4
|Apr 30, 2015||AS||Assignment|
Owner name: APPLE INC., CALIFORNIA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:AUTHENTEC, INC.;REEL/FRAME:035552/0286
Effective date: 20130210